INDEX

Explanations

terms related to pilot projects and experimental programs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anzi

-0.17

 lÃ´

-0.17

æĹı

-0.16

emes

-0.16

_TER

-0.15

 pupper

-0.15

OAD

-0.15

edik

-0.15

eyh

-0.14

CTYPE

-0.14

POSITIVE LOGITS

è©¦

0.18

0.17

 trial

0.16

Cho

0.15

rego

0.15

 trails

0.14

 Trial

0.14

Kit

0.14

arp

0.14

Activations Density 0.055%

terms related to pilot projects and experimental programs

No Comments

No Known Activations